显示语言 中英对照 中文 English
点击段落跳转到对应时间
0:00 今年一月,我告诉全世界,Mac Mini 将成为本地 AI 的王者。我还说 Apple 会赢下本地 AI 竞赛,大家都说我疯了。 Back in January, I told the world that the Mac Mini was gonna be the king of local AI. I also said Apple was gonna win the local AI race. People called me insane. 0:11 他们在社交媒体上把我喷惨了，就因为我那么说。不过我刚拿到全新的 Mac Mini M6，今天我们就来证明他们全都错了。 They destroyed me on social media for saying that. Well, I just got the brand-new Mac Mini M6, and we're gonna prove them all wrong. 0:21 我要尝试把这台机器的性能彻底推到它的绝对极限。 I'm going to attempt to push this thing to its absolute limits. 0:25 我会教你在 Mac Mini 上用最简单的方法加载本地 AI 模型,完全不需要技术背景。然后看看它能扛住什么样的工作负载。 I'm gonna show you how to load up local AI models on a Mac Mini, the absolute easiest way possible, no technical skills required. Then we're gonna see what kind of workloads this thing can handle. 0:37 你能退掉云端订阅吗?只用一台 Mac Mini 就能取代 ChatGPT 吗?我们来一探究竟。还是说它会啥都跑不动,让我颜面扫地? Can you cancel your cloud subscriptions? Can you cancel ChatGPT with just a Mac Mini? We're gonna find out. Or will there be egg all over my face 'cause this thing won't be able to handle anything? 0:48 开始实测。我要把它插上电,看看在 Mac Mini M6 上跑本地 AI 能做什么。这次绝对会让你大吃一惊。准备好了,开始。 Let's put it to the test. I'm gonna plug this sucker in, and we're going to see what we can do with local AI on a Mac Mini M6. This one is going to surprise you. Let's lock in and get into it. 1:01 好,我刚把 Mac Mini 插上了。你们可以看到参数:这是一台 M6,配备 32GB 的 RAM。我们开始吧,先教你怎么加载本地模型。 All right. So I just plugged the Mac Mini in here. You can see the stats. It is an M6, uh, with 32 gigabytes of RAM. Let's get this going. Let me show you first how we're gonna load local models in. 1:12 这绝对是做起来最简单的方法。我们要做的，就是打开 Hermes Desktop。 This is the absolute easiest way to do it. What we're going to do is we are going to load up Hermes Desktop. 1:18 介绍一下:Hermes Agent 是一款很棒的开源 AI 智能体,运行在你的电脑上,是你的私人助理、私人 AI 员工,支持任何模型,云端本地都行。 So for those who don't know, Hermes Agent is a fantastic open source agent, runs on your computer, is your own personal assistant, your own personal AI employee, and can be used with any model out there, both cloud and local. 1:32 那我现在就来下载，想跟着我一起做的就同步操作。接下来的一切都完全免费、简单，不需要任何技术基础。 So I'm gonna download this now. If you wanna follow along with me, do it with me here. It's completely free. Everything I'm about to show you is completely free, easy, no technical skills required. 1:41 我会把 Hermes 应用拖进应用程序文件夹,这在 Mac 上还是惯例。然后打开 Hermes。好,安装超级简单。 I will move the Hermes application into Applications 'cause that's something you still do on Mac. Then we're gonna load up Hermes here, and we're gonna open it up. All right. Installation, super easy. 1:52 它会自动下载并准备好,无需技术。 It's gonna download everything, get it prepared. Again, no tech needed here. 1:55 接下来演示如何用 Hermes 找出哪些 AI 模型能在 Mac Mini 上本地运行,再加载并开始使用。我正在安装 Hermes Desktop。 And then I'm gonna show you how we're gonna use Hermes to figure out which AI models we can run locally on our Mac Mini and then actually load them up and start using it. Okay, so I'm installing Hermes Desktop. 2:07 它会自动设置好。Hermes 是很棒的本地开源 AI 智能体,加载任何模型都很简单,还能帮你装本地模型。 That's gonna get set up. For those who don't know, Hermes, amazing local open source AI agent, makes it really easy to load in any model you want. It'll even load local models for you. 2:17 它会帮你找到最佳本地模型并加载,超简单。纯新手也行,从没加载过也没关系,跟着我做就好。 It'll find the best local model for you and load it. Super easy. We're gonna have this set up. Straight up beginners can do this. Even if you've never loaded a local model before, you can do what I'm doing, so follow along with me. 2:26 我也会把 Hermes Desktop 的链接放在下方,完全免费。装完了,只用了 45 秒。启动。砰,进入 Hermes Agent 了。 I'll put a link down for Hermes Desktop too, completely free. All right. All installed. Took, like, 45 seconds. Let's launch this up. And boom, we are in Hermes Agent. 2:36 现在加载本地模型。这个功能很棒。说明一下:这条视频完全没有任何赞助。 Now let's load up a local model. They have super nice function out here. They don't- there's no one sponsoring this video. This is a completely unsponsored video. 2:45 我推荐这一切,只因为我认为它就是最强的。现在进入 Hermes Agent 右上角的设置。 Everything I'm telling you here is because I think it's the absolute stone-cold best. Let's go into Settings in the top right of Hermes Agent here. 2:53 接下来点 Providers,然后选择本地运行模型。 Next, we're gonna go to Providers, and then we're going to go Run models locally. 2:59 Hermes Agent 会自动判断哪个模型最适合在你的电脑上本地运行。对我来说,它选了 Qwen 3635B。 What will automatically happen is your Hermes Agent will decide what is the best model to run locally on your computer. For me, it was Qwen 3635B. 3:10 如果你跟我一样,有一台 32GB 内存的 Mac Mini,不算少,也不算多,刚刚好。我们现在就能运行 Qwen 3635B,这是个很棒的模型。 So if you're like me, you have a Mac Mini that's 32 gigs of memory. It's not a terrible amount. That's not a huge amount. That's a decent amount. We can now run Qwen 3635B. This is a great model. 3:21 很多人拿它和 Opus 4 或 5 比,差不多那个水平。当年的 Opus 4 或 5 很炸裂,发布时震惊了所有人。 A lot of people compare this to, like, Opus 4 or 5, somewhere in that area. For those who don't remember, Opus 4 or 5 back in the day, that was sick. That was mind-blowing when it came out. 3:32 现在它就在你桌上的 Mac Mini 本地运行。我们来设置：只要点一下"帮我设置"，它就会开始下载。 Now it's running locally on your desk on a Mac Mini. So let's set this up. All you gotta do is click Set Up For Me. Bada bing, bada boom, it's gonna start downloading it. 3:40 大约 21GB,所以硬盘需要留出 21GB 空间来下载,不算太多。 It's about 21 gigs, so you need 21 gigs on your hard drive, uh, to download it. Not too much. 3:46 再过四分钟，我们就会拥有一个达到去年 Opus 水平的模型，而且它完完全全靠这台 Mac Mini 本地运行。 And in four minutes, we are going to have a Opus-from-last-year level model running completely on a Mac Mini. 3:56 不需要联网,不用云端订阅,一分钱不花,全部本地运行。但它到底好不好用?马上见分晓。 No internet required, no cloud subscription. Don't have to pay for anything. It's all gonna be running locally. But we'll see how g- Is it gonna be any good? We're about to find out. 4:05 顺便说,加载完后我会讲讲本地模型的优缺点。如果你在想“为什么要用本地模型”,马上就会讲清这么做的全部好处。 By the way, right after we load this, I'll go over kinda all the strengths and weaknesses of local models. If you're thinking, "Why the hell would I wanna load a local model?" We'll go through that in a second. I'll go through all the advantages of why you'd wanna do something like we're doing here. 4:16 先加载,再测试。 For now, let's get this loaded, and let's test it out. 4:19 趁模型加载的时候,我快速讲讲在 Apple 上做本地 AI 的优势,以及我为什么看好它:第一,你可以把 Apple 设备的全部内存都用于 AI。 And real quick, as the model is loading, let me just take you through what are the advantages of doing local AI on Apple, why I'm bullish, is because, number one, you can use the full memory of your Apple device for AI. 4:32 啥意思? What does that mean? 4:33 Apple 设备采用的是统一内存,也就是说你电脑上的内存,比如这台 Mac Mini 的 32GB 内存,也可以全部用于图形处理。 Apple devices have what's called integrated memory, meaning the memory you have on your computer, this Mac Mini, for instance, 32 gigabytes of memory, that can be used for all graphical processing as well. 4:45 这意味着全部 32GB 都可以用来加载本地模型,这很惊人,因为即使是顶级的 Nvidia 芯片——别误会,Nvidia 非常棒,是改变世界的芯片,优点很多。 That means all 32 gigabytes can be used to load up local models. That's a lot because even top-of-the-line Nvidia chips, which, don't get me wrong, Nvidia, incredible, world-changing chips, tons of strengths. 4:58 我有很多关于 DGX Spark 之类的视频,一定要去看看。但 Apple 芯片的优势是可以加载更大的模型,因为你可以把全部内存都用于这些模型。 I have a lot of videos on DGX Sparks and all that. Definitely check that out as well. But the advantage of Apple chips is you can load bigger models because you can use all of your memory for those models. 5:09 所以即使这台电脑不到一千美元,我们也能加载大模型,因为所有内存都能用于本地模型。而且还有很多软件优势,体验很棒。 So even though this is a cheaper sub-$1,000 computer, we can load big models onto it because all the memory in it can be used for local models. On top of that, there's a lot of software advantages. It's a great UX. 5:21 我觉得 macOS 的体验很好,很多人用它作为日常主力机来工作,所以现在你用来日常工作的这台设备上,也能同时跑你的本地 AI。 I think macOS is a great UX. A lot of people use it as their daily driver to do work, so now the thing you're using for your daily driver to do work, you also have your local AI running on it as well. 5:32 所以如果你在做创意工作,现在你可以在同一台用来工作的设备上生成图像。这些就是选择 Apple 设备的主要优势。 So if you're doing creative work, now you can generate images on the same device you're using to do your work. And so these are the big advantages of going with an Apple device. 5:42 再说一次,Nvidia 电脑也有自己的优势。我有一台 5090,能跑本地 AI 模型,速度快得离谱。 And again, Nvidia computers, they have their own advantages. I have a 5090. I'm able to run local AI models, and they are lightning fast like crazy. 5:51 在 Apple 芯片上性能会稍弱一些,不过新款 M5 Ultra 很值得期待。 It will be a little bit less performant on Apple chips, although the new M5 Ultra... 5:57 顺便说一下,再过几周我就会展示 M5 Ultra,也就是 512GB 的 Mac Studio。 By the way, I will be showing off the M5 Ultra, the 512 gigabyte Mac Studio, in just a couple weeks now. 6:03 一定要马上订阅并打开通知,因为那条视频一出绝对会炸裂全场,那是改变世界的技术,记得打开通知。 Make sure to subscribe and turn on notifications immediately for that 'cause when that video drops, that's gonna be an absolute stone-cold banger. That's gonna be world-changing technology. Turn on notifications for that. 6:14 不过目前 Apple 在速度方面还在追赶,我们看看 M5 Ultra 会带来什么。这些就是选择 Apple 电脑的优势。另外这里列出的还有最直观的价格。 But at the moment, Apple's still catching up a little bit on the speed side. We'll see what the M5 Ultra brings us in a little bit, though. So these are the advantage of going with an Apple computer. Also, now listed here is just straight-up price, right? 6:26 Mac Mini 八九百美元就能买到,还能跑本地模型,相当惊人。好,回到 Hermes。看来已经加载好了,我们回到了 Hermes 界面,点击这里选择模型。 Mac Mini, you can get it for, like, $800, $900 and run a local model. That's pretty mind-blowing. All right. Let's get back to Hermes. All right. It looks like it must have been loaded 'cause we're back at the Hermes screen. Let's click here to choose a model. 6:38 往下滚动,本地 Qwen3 35B,点击它。好,加载完成了,模型就在这儿。第一次看本频道的观众,这是 Hermes Agent,你的专属 AI 员工。 I scroll down. Local Qwen 3635B. Let's click on that. All right. So we got it loaded. The model's right there. For those who are brand new to the channel, this is Hermes Agent. It's your own AI employee. 6:49 你可以让它做任何事。它能控制电脑、构建东西、对话、回答问题,现在由本地模型驱动。 You can ask it to do whatever you want. It has control over your computer, can build things, can talk to you, can answer questions. It is now powered by our local model. 6:57 先回答第一个问题:Mac Mini 能加载本地模型吗?可以,现在 Qwen3 已经跑在里面了。再看看它的表现。 So first of all, to answer the first question, can you load local models onto a Mac Mini? Well, the answer is yes. We now have Qwen 36 in here. But let's see how it performs. 7:06 如果它又烂又慢又难用,那就没什么意义了。但先看看它到底有多强。嘿,你在吗?我按下回车,看看会发生什么,看看性能表现如何。 If it stinks and is slow and sucks, then, well, it's gonna be kinda pointless. But let's see how good this is. Hey, are you there? And I'm gonna hit Enter. Uh, let's see what happens. Let's see what type of performance. 7:18 顺便给不了解的人说一下:第一次给本地模型发提示词会花更久一点,因为要先把模型加载进内存,就像你刚才看到的那样。 So for those who don't know also, by the way, the first time you send a prompt to a local model, it's gonna take a little bit longer. They have to load it into memory. So just, as you saw there, load into memory. 7:29 接下来就会快很多。另外,如果你在跟着操作,而且这是你第一次成功加载本地模型,恭喜你,你应该给自己点个赞。 Now, moving forward, it's going to be much faster. Also, by the way, if you're following along and this is your first time loading up local models and you just did it, congratulations. You should give yourself a pat on the back. 7:40 你应该为此感到自豪。你刚刚把人类历史上最重要的技术加载到了自己的电脑上,现在它就在你的桌面上运行。 You should feel good about that. You just loaded the most important technology in the history of our species onto your own computer, and now it's running on your desk. 7:52 这很惊人。“嘿,我在。我能为你做什么?既然是第一次对话,先建个简单档案,让我更有用。”我是 Alex Finn。 That is pretty amazing "Hey, I'm here. What can I do for you? Since this is our first conversation, why not set up a quick profile so I can be more useful?" I'm Alex Finn. 8:02 我是一名内容创作者，也是一名创业者，我平时制作的内容全部都是关于 AI 的。来吧，跟我的观众们打个招呼。 I'm a content creator and entrepreneur. I create content about AI. Say hi to my audience. 8:13 马上我们做个性能测试，看看有多快。你看，能看到它思考的过程，全显示在这里。我存进记忆，速度相当快。 And in just in a second, we'll do a kind of a, a performance check here, see how fast this is. But you look, look at this. You can see how it's thinking. So I see all the thinking here. Let me save that to memory. This is pretty fast. 8:23 说实话，这是现场直播，我没做任何预测试。这真是我第一次用这台 Mac Mini 做这件事。“Alex，这是可以分享的消息。”“大家好，我是 Alex Finn。”对，我就是 Alex Finn。 I'll be honest, I'm doing this live with you. I did not do any sort of pretests or anything. Like, literally, this is my first time doing this with this Mac Mini. "Hey, Alex, here's a message you can share." "Hey, everyone, I'm Alex Finn." Well, I'm Alex Finn. 8:34 “一位深入探索 AI 世界的内容创作者和创业者。敬请关注。可以随意修改。你通常在哪发内容？YouTube、X？”那些平台都发。我可没剪辑过。 "A content creator and entrepreneur diving into the deep world of AI. Stay tuned. Feel free to tweak it however you like. Where do you usually post your content? YouTube, X?" Uh, all of those places. I, th- I did not edit this. 8:45 你刚才看到的完全是实时的。它的响应速度非常快，感觉和云端 AI 一样快。它在为自己创建记忆，所以能记住东西。 What you just saw was completely real time. It's responding very, very quickly. I mean, that feels like it's as fast as cloud AI. It's creating memories for itself, so it's remembering things. 8:57 这智能水平真的很棒。现在看到的，一两年前还是令人惊叹的前沿技术。现在我在一台 Mac Mini 上本地运行它，就是这台，就在我桌上。 This is really good intelligence. What we're seeing here, like a year or two ago, would've been mind-blowing frontier. Now I'm running it locally on a Mac Mini. This is the one we're demoing on right now. It's on my desk over here. 9:08 不过我有大概二十台 Mac Mini，我是个 Mac Mini 狂热粉。总之开始吧，测测它到底能有多好。速度测过了，确认相当快。 But I have like 20 Mac Minis by the ... I'm like a Mac Mini freak. Anyway, so let's do this. Let's test, let's see how good this can be. We tested the speed. We verified the speed is pretty dang good. 9:19 现在做这个，给你们看看时间戳。看到没？12点34分发的提示词，12点34分就有回答。不到一分钟就响应，不到一分钟就收到回复。好了。 Now let's do this, and like, let, I'll even show you, like, the timestamps here. See this? 12:34 is when we sent the prompt. We got the answer at 12:34. So less than a minute it's responding. Less than a minute we're getting responses here. All right. 9:30 让它做个有趣的东西。你能用单文件 HTML 给我做个贪吃蛇游戏吗？好，看看它开发应用的实际速度有多快。 Let's do, let's have it build something interesting. Can you build me a snake game using single-file HTML? All right. Let's see how fast it can actually build us apps. 9:42 它能做应用吗？先从小项目开始，比如贪吃蛇游戏，再做更高级的，比如 3D 第一人称射击游戏。开始。用户想要单 HTML 文件的贪吃蛇游戏。 Is this usable for apps? We'll start with something small, like building a snake game. Then we'll get to something a little bit more advanced out, maybe like a 3D first-person shooter. So here we go. The user wants a snake game in a single HTML file. 9:54 让我做一个完整精致的版本。我喜欢能看到它的思考过程，这是本地 LLM 的又一个优势。测试做完后我会详细讲，给你们好好上一课。 Let me build a complete polished one. I love how you can see the thinking. That's another one of the advantages of local LLMs. And again, it- Advantages of local LLMs. Right after we do these tests and everything, I'll go through that. I'll educate you. I'll get your brain bigger. 10:05 我会让你脑洞大开。最厉害的是能看到全部思考过程。用云端模型时，思考过程通常是隐藏的，你不知道模型怎么工作。 We'll get your, uh, uh, Abdullah Obligata bigger. But what's amazing about that you can see all the thinking, right? A lot of the times when you use cloud models, the thinking is hidden, so you don't really know how the models work. 10:17 但模型在你自己电脑上本地运行，一切都发生在这里，没有任何数据传到互联网或云端。 But because you're running the models locally on your own computer, everything happens in here, right? Nothing goes to the internet, nothing goes to the cloud. 10:26 一切都在本地发生，所以你能看到它思考和运作的方式。你完全掌控它的工作方式，这就是为什么我认为本地 LLM 就是未来。 Everything happens locally, so you're able to see the way it thinks, the way it operates. You have full control over how it works, and that's why I believe, in a lot of ways, local LLMs are the future. 10:38 它们是未来，因为一切都将私密，都在本地发生。 They are the future of what most people are using 'cause it's gonna be private. It's all gonna happen locally. 10:44 你的隐私数据都不会上传云端，想想就很了不起，所有惊人的计算就发生在这里。 None of your private details and data go to the cloud, and that's pretty amazing to think about, that all this incredible computation's happening just right here. 10:52 就在我说话时，这全是实时的，游戏正在构建。看起来快完成了，一下子写了78行代码。好，我在浏览器里打开它。 And as I was speaking, again, this is all real time, uh, the game is being built. Looks like we're almost h- uh, done here. It looks like I wrote a good amount, 78 lines of code just like that. All right, so I'm gonna open this in my browser. 11:04 来测试一下。跑起来了。好，吃到豆子了，蛇变长了。能用，真的能用。标题还在屏幕上，没关系。 Let's, let's test this out. And it's going. It's going. Okay, so I'm getting the, the cookies. Uh, the snake's getting bigger. It works. It works. The snake title's still on the screen. That's fine. 11:16 等下再让它改——不是吧，放角落？认真的？看看这操作，这才是技术。看直播没人能做到。我可是天生玩家，居然吃到角落豆子。 We can prompt in a second to fi- oh, come on, you're gonna put it in the corner? Are you serious? Oh, look at this. Look at skills. That's skills, baby. No one watching this can do that. I'm true born gamer right here, the fact that I can get that corner cookie. 11:27 好，看看死了会怎样。砰，游戏结束，分数出来了。这完全是本地构建的。升级难度，这样问它。 All right, let's see what happens when we die here. Boom, game over. We got our score. That was built completely locally. Let's take it to another level. Let's say this. 11:35 "你能不能只用单个 HTML 文件，就给我做出一个 3D 的第一人称射击游戏来？" "Can you build me a single-file HTML 3D first-person shooter?" 11:44 再次强调，完全本地运行，用的只是一台不到一千美元的 Mac Mini。好了，完成了，这就是你的 3D 射击游戏。 Again, completely local, all on a Mac Mini that you can get for under $1,000. All right. Boom, it's done. Here's your 3D shooter. 11:53 它有完整的 3D 引擎、大量敌人，可以玩、射击、换弹、还有枪口火光。好，我们来玩。我在浏览器里加载，开始了，我们有…… Has entire 3D engine, t- tons of enemies, be able to play the game, shoot, reload, muzzle flash. All right, let's play this. Let me load this up in a browser. Here we go. Let's start. Uh, we have... 12:04 它说像德军总部，确实很像。我们在玩。哦，我在射击敌人，打中了。获得经验值，右上角有地图。 It said it was like Wolfenstein, that's for sure. It definitely looks like it. We're playing it. Ooh, I'm shooting the enemy. I'm shooting the enemy. Got experience points. Map in the top right. 12:14 这是史上最好的 3D 射击游戏吗？不是，但重点不在这。 Is this the prettiest, best 3D first-person shooter of all time? No, and that's not the point. 12:19 这并不是一个前沿的云端大模型，但它是一个完全在本地运行的模型，而且跑在你现在能买到的最便宜的电脑上。 This isn't a frontier cloud model, but this is a model running completely locally on, like, the cheapest computer you possibly can buy. 12:30 人类有史以来最先进的技术——人工智能，正百分之百运行在你桌面上这台小电脑上。这句话我敢这么说。 You have the most advanced technology of all time, artificial intelligence, running 100% on your desk on a computer this small. I will say this. 12:41 如果两年前我给你看云端模型的这个演示,你绝对会被震撼到。跟今天的 Opus 5.5 比够好吗?不,不够好。 If I showed you that demo two years ago from a cloud model, you would've been blown away. You would've been absolutely blown away. Is it great compared to, like, Opus 5.5 today? No. No, it's not. 12:53 但重点是:它在本地运行,完全私密、安全,跑在你自己的电脑上。下面进入总结。 But the point is this: it is running locally, completely private, secure, running on your own computer. So let's go into conclusions. 13:01 接下来聊聊本地 AI 的所有优势,以及为什么你该照做。结论:Mac Mini 能跑本地 AI 吗?我认为能。 Then we'll talk about all the advantages of local AI and why you wanna do what I just showed you. Conclusion, can you run local AI on a Mac Mini? Yes, I think you can. 13:11 你不仅能跑 Qwen 3.6 这样很聪明的模型,相当于一年前的前沿水平,而且速度也相当不错。所以那种「Mac Mini 跑不了」的说法, Not only can you run really smart intelligence like Qwen 3.6, which again is like frontier from a year ago, but it's also pretty good speed. So that whole thing, "Oh, you can't do it on Mac Mini. 13:23 「Alex Finn 错了」已经不成立,我是对的,刚证明给你看,证据确凿。「可,Alex,我能用 ChatGPT,也能用 Opus, Alex Finn is wrong," that's dead. I'm right. I just proved it. I have the receipts. I just showed you. "But okay, but Alex, uh, I can use ChatGPT. I can use Opus. 13:33 为什么要这样做、还买台电脑?」几点原因。第一,这是免费的。当然电脑要花钱,但这台大概八九百美元。 Why would I do this and buy a computer?" Well, a few things. One, this is free. Yes, you have to pay for the computer itself, but I-- this, I think, was like an eight or $900 computer. 13:42 如果你每月花 200 美元订 ChatGPT,而这个智能水平对你够用,大概四个月就回本。长期看是省钱,而且私密。 Now, if you're paying $200 a month for ChatGPT and this level of intelligence is good for you, you have it paid off in like four months. So long term, you're saving money. It's private. 13:54 现在你发提示词给 AI 模型,它会去云端、数据中心和服务器,不停留在你电脑上,所以你说的话并不完全属于你。 When you send prompts to your AI model right now, it goes to the cloud. It goes to data centers and servers. It does not stay on your computer, so the things you're saying are not totally yours. 14:06 并不完全私密。而在 Mac Mini 或任何电脑上跑本地模型,比如 Nvidia 设备,它是安全的,留在你电脑上,完全私密。 It's not totally private. When you do a local model on a Mac Mini or any computer you have, on an Nvidia, whatever, it is secure. It stays on your computer. It's completely private. 14:17 哪怕断网也照样能用,你完全掌控。想定制这个模型,可以;想训练一个叫 LoRA 的东西,让它变成你自己的、带上你的风格,也可以。 I mean, you can be disconnected from the internet, and it's still going to work. You have total control. If you wanna customize this model, you can. If you wanna train what's called a LoRA and make it your own and give it your own voice, you can do that. 14:29 想学就在评论区留言。想看进阶的本地 AI 视频吗,比如训练模型、LoRA 之类?评论告诉我,我会做给你看。而我认为这才是最重要的部分。 If you wanna learn how to do that, let me know down below. Do you want like advanced local AI videos, like how to train the model, LoRAs, things like that? Let me know down below in the comments. I'll make like an advanced local AI video for you. And I think this is the most important part of it all. 14:42 每次我说「试试这个 AI」,最多的评论就是:「ROI 呢?投资回报呢?我什么时候能回本?」 You know, every time I say, "Try this AI, try that," I think the number one comment is, "Well, what's the ROI? What's the ROI with that? When will I make back my money?" 14:50 我认为生活里不是每件事都得像做一笔 ROI 投资那样去算回报。 I don't think everything you have to do in your life has to be like an exercise of ROI. 14:56 我觉得不必把每分钱都列进表格,说什么「第六周没回本我就不做」。你完全可以只为好玩而做一件事。 I don't think you need to map out every penny you spend on like a spreadsheet and like, "Oh, if I don't get my ROI by week six, I'm not gonna do..." I think you're allowed to do things for the fun of it. 15:06 虽然本地 AI 还有很多别的优势,但我认为你完全可以因为它好玩而去做,而这真的非常非常好玩。 And while I do believe there are tons of other advantages to local AI, I think you're allowed to do things because it's fun, and this is extremely fun. 15:16 买一台电脑，在上面跑本地 AI，拥有一个完全属于你自己的私人智能，这件事真的非常有趣。 It's extremely fun getting a computer and then running local AI on it and having, like, your own personal private intelligence. 15:24 我觉得这特别好玩。如果你在看 Alex Finn 频道,是 Finn Fam 的一员,我允许你去玩,你可以尽情享受乐趣。 I think that's extremely fun, and if you're watching this, if you watch, uh, the Alex Finn channel, you're a member of Finn Fam, I give you permission to have fun. You're allowed to have fun. 15:36 所以如果你就想做,不在乎 ROI,那就去做,开心去做。这也非常有教育意义:你在学习我们这辈子最重要的技术——AI。 So if you just wanna do this, and you don't care about the ROI, then do it. Have fun and do it. It's also extremely educational. You're learning about the most important technology of our lifetimes, AI. 15:48 你是在用最直接动手的方式学习它——把它装进自己的电脑本地运行。这就是纯粹的学习,我认为这很重要。 You're learning about it in the most, basically, hands-on way you possibly can by loading it locally on your own computer. And so it's just straight-up educational, and I think that's important. 15:58 AI 会存在很久,还会再扩大一万倍,基本上会掌控世界经济。所以你应该去学它,应该亲自动手。 I think AI's gonna be around for a long time. I think it's only gonna get 10,000 times bigger, and I think it's gonna basically control the world economy. So you should be learning about it. You should be hands-on. 16:09 你应该成为 AI 专家,这就是很好的方式。学到东西了吗?点个赞。我有地球上第一的 AI 通讯,叫 Ship It Weekly,链接在下方。 You should be an AI expert, and this is a great way to do that. Did you learn anything at all? Leave a like down below. I have the number one AI newsletter on planet Earth. Link for that down below. It's called Ship It Weekly. 16:21 Ship It,链接在下方,去订阅吧。希望这期有帮助。告诉我下期想听什么:更多本地 AI?更多 Claude Code?还是更多实战搭建?评论区告诉我。 Ship It, link down below. Join that. I hope this was helpful. Let me know what you want me to cover in the next video. You want me to cover more local AI stuff? You want me to cover more kinda Claude code stuff? You wanna see more building stuff? Let me know down below. 16:33 希望这期对你有帮助,希望你喜欢。非常感谢收看,我真的很感激你选择跟我学习。我们下期见。 I hope this was helpful. I hope you enjoyed it. Thank you so much for watching the channel. I am so deeply appreciative you choose to learn from me. Thank you so much. See you in the next video.
没有匹配的文稿
28:00
70:10
14:46